4 papers
Toward a Physical Theory of Intelligence
Peter David Fagan
While often treated as abstract algorithmic properties, intelligence and computation are ultimately physical processes constrained by conservation laws. We introduce the Conservati…
Keyed Chaotic Dynamics for Privacy-Preserving Neural Inference
Peter David Fagan
Neural network inference typically operates on raw input data, increasing the risk of exposure during preprocessing and inference. Moreover, neural architectures lack efficient bui…
Learning from Demonstration with Implicit Nonlinear Dynamics Models
Peter David Fagan, Subramanian Ramamoorthy
Learning from Demonstration (LfD) is a useful paradigm for training policies that solve tasks involving complex motions, such as those encountered in robotic manipulation. In pract…
SECURE: Semantics-aware Embodied Conversation under Unawareness for Lifelong Robot Learning
Rimvydas Rubavicius, Peter David Fagan, Alex Lascarides +1
This paper addresses a challenging interactive task learning scenario we call rearrangement under unawareness: an agent must manipulate a rigid-body environment without knowing a k…